An Adaptive Deep Learning Optimization Method Based on Radius of Curvature

An adaptive clamping method (SGD-MS) based on the radius of curvature is designed to alleviate the local optimal oscillation problem in deep neural network, which combines the radius of curvature of the objective function and the gradient descent of the optimizer. The radius of curvature is consider...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhang, Jiahui, Yang, Xinhao, Zhang, Ke, Wen, Chenrui
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Hindawi 2021
Materias:
Research Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8598332/
https://www.ncbi.nlm.nih.gov/pubmed/34804152
http://dx.doi.org/10.1155/2021/9882068

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8598332/
https://www.ncbi.nlm.nih.gov/pubmed/34804152
http://dx.doi.org/10.1155/2021/9882068

Ejemplares similares